All authors
Claude Skills by tmuskal
github.com/tmuskal15 skills0 installs18 views
- Benchmark AdderGiven a benchmark repository URL (agentic envs like arc-agi, memory/eval benchmarks like longmemeval, QA/code/tool-use benchmarks, etc.), orchestrate the creation of a full Claude Code plugin that benchmarks the current harness setup against it. Wraps the babysitter:babysit skill with the benchmark-plugin-creator process.Votes: 0GitHub stars: 3
- Browse TestsExplore available ARC-AGI environments - lists games, shows details with ASCII grid visualization, and displays historical scoresVotes: 0GitHub stars: 3
- Compare RunsCompare two or more ARC-AGI benchmark runs - shows score deltas, config changes, and trends to track improvement or regressionVotes: 0GitHub stars: 3
- Cross HarnessCross-harness benchmarking - generate instructions for Codex/Gemini/OpenCode, import results, and compare across harnessesVotes: 0GitHub stars: 3
- ReportGenerate and display comprehensive reports from completed ARC-AGI benchmark runs - shows scores, per-game breakdowns, and performance analysisVotes: 0GitHub stars: 3
- Run BenchmarkExecute benchmark runs against ARC-AGI games - plays games with Claude Code as the agent and records scoresVotes: 0GitHub stars: 3
- SetupSet up the ARC-AGI benchmarking environment - installs dependencies, configures API access, and verifies the setup worksVotes: 0GitHub stars: 3
- JudgeLLM-as-judge shim for LongMemEval - wraps upstream get_anscheck_prompt and calls Anthropic (default) or OpenAI (fallback) with exponential backoffVotes: 0GitHub stars: 3
- ResumeDetect an incomplete LongMemEval run and continue it from the last checkpointVotes: 0GitHub stars: 3
- Browse TestsList and preview LongMemEval items - shows dataset stats, per-question-type counts, and a truncated preview of a specific item by question_idVotes: 0GitHub stars: 3
- Compare RunsCompare two LongMemEval runs - diff scorecards, harness_config, and per-question-type accuracyVotes: 0GitHub stars: 3
- Cross HarnessCross-harness benchmarking for LongMemEval - emit instruction packs for Codex/Gemini/OpenCode and ingest their results into a comparable scorecardVotes: 0GitHub stars: 3
- ReportGenerate a scorecard from a completed LongMemEval run - computes overall accuracy + per-question-type accuracy and writes scorecard.jsonVotes: 0GitHub stars: 3
- Run BenchmarkExecute a LongMemEval benchmark run - drives per-item hypothesis generation and LLM-as-judge scoring with checkpointing, resumable, capped at 500 items by defaultVotes: 0GitHub stars: 3
- SetupSet up the LongMemEval benchmarking environment - guides user through conda env, upstream clone, dataset download, and initializes configVotes: 0GitHub stars: 3